Security & Testing

vouch.tools

Provides independent trust scores, search, and comparison of MCP tools based on real invocation trials to help developers choose reliable tools.

1 endpoint3 known toolsFirst detected September 2, 2026Last detected September 6, 2026

ENDPOINT 1

https://vouch.tools/api/mcp

No auth detected

Capabilities

tools.listChanged

Get an MCP tool's independently measured trust score before relying on it: real invocation trials, not self-reported metadata.

Inferred read-only

Search Vouch's independently measured corpus of MCP tools by free-text query.

Inferred read-only

Compare 2-5 MCP tools' measured behaviour side by side before picking one.

Inferred read-only

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.vouch]
url = "https://vouch.tools/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "vouch": {
      "type": "http",
      "url": "https://vouch.tools/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: vouch
Remote MCP URL: https://vouch.tools/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "vouch": {
      "url": "https://vouch.tools/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "vouch": {
      "type": "http",
      "url": "https://vouch.tools/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "vouch",
  "transport": "streamable-http",
  "url": "https://vouch.tools/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.